As the fundamental problem in the computer vision area,image matching has wide applications in pose estimation,3D reconstruction,image retrieval,etc.Suffering from the influence of external factors,the process of imag...As the fundamental problem in the computer vision area,image matching has wide applications in pose estimation,3D reconstruction,image retrieval,etc.Suffering from the influence of external factors,the process of image matching using classical local detectors,e.g.,scale-invariant feature transform(SIFT),and the outlier filtering approaches,e.g.,Random sample consensus(RANSAC),show high computation speed and pool robustness under changing illumination and viewpoints conditions,while image matching approaches with deep learning strategy(such as HardNet,OANet)display reliable achievements in large-scale datasets with challenging scenes.However,the past learning-based approaches are limited to the distinction and quality of the dataset and the training strategy in the image-matching approaches.As an extension of the previous conference paper,this paper proposes an accurate and robust image matching approach using fewer training data in an end-to-end manner,which could be used to estimate the pose error This research first proposes a novel dataset cleaning and construction strategy to eliminate the noise and improve the training efficiency;Secondly,a novel loss named quadratic hinge triplet loss(QHT)is proposed to gather more effective and stable feature matching;Thirdly,in the outlier filtering process,the stricter OANet and bundle adjustment are applied for judging samples by adding the epipolar distance constraint and triangulation constraint to generate more outstanding matches;Finally,to recall the matching pairs,dynamic guided matching is used and then submit the inliers after the PyRANSAC process.Multiple evaluation metrics are used and reported in the 1st place in the Track1 of CVPR Image-Matching Challenge Workshop.The results show that the proposed method has advanced performance in large-scale and challenging Phototourism benchmark.展开更多
For the virtual environment (VE) to control remote robots through Internet, this paper proposes an operational idea based on virtual guides (VGs). The VGs consist of three types, line VG, plane VG, and body VG, which ...For the virtual environment (VE) to control remote robots through Internet, this paper proposes an operational idea based on virtual guides (VGs). The VGs consist of three types, line VG, plane VG, and body VG, which can greatly enhance the safety and flexibility of the man-machine system. Through the analysis of several common cases, the idea of the VGs are first introduced and described. Second, detailed descriptions of the three VGs are given, and then a uniform representation of all VGs is given. Finally, a typical experiment is designed and implemented according to the modes of video feedback, video&VE feedback, and video&VE&VG feedback. Experimental results show that the operation based on VEs and VGs have significant advantages over that based on video feedback, and VGs can greatly improve the ability of the VE to control remote robots, thus obtaining high and efficient man-machine cooperation.展开更多
The paper is a part of wider investigation related to the application of basic sciences to the sustainable development of society.It deals with the presentation of knowledge to the real estate(fast growing business)ab...The paper is a part of wider investigation related to the application of basic sciences to the sustainable development of society.It deals with the presentation of knowledge to the real estate(fast growing business)about the local natural and man-made hazards in the near vicinity of any structure(inhabitant,recreation area,land,etc.)and their influence to the social safety and human comfort of life.The structure,necessary information and knowledge base for visible or hidden hazards about a guide for the real estate business is included.An example of application the knowledge about seismic hazard and related phenomena simplified to be more available to the non-specialists(such as real estate agents and companies)targeted to Sofia(the largest urban center and capital of Bulgaria)can attract and improve the learning abilities of the real estate for the society’s sake.展开更多
文摘As the fundamental problem in the computer vision area,image matching has wide applications in pose estimation,3D reconstruction,image retrieval,etc.Suffering from the influence of external factors,the process of image matching using classical local detectors,e.g.,scale-invariant feature transform(SIFT),and the outlier filtering approaches,e.g.,Random sample consensus(RANSAC),show high computation speed and pool robustness under changing illumination and viewpoints conditions,while image matching approaches with deep learning strategy(such as HardNet,OANet)display reliable achievements in large-scale datasets with challenging scenes.However,the past learning-based approaches are limited to the distinction and quality of the dataset and the training strategy in the image-matching approaches.As an extension of the previous conference paper,this paper proposes an accurate and robust image matching approach using fewer training data in an end-to-end manner,which could be used to estimate the pose error This research first proposes a novel dataset cleaning and construction strategy to eliminate the noise and improve the training efficiency;Secondly,a novel loss named quadratic hinge triplet loss(QHT)is proposed to gather more effective and stable feature matching;Thirdly,in the outlier filtering process,the stricter OANet and bundle adjustment are applied for judging samples by adding the epipolar distance constraint and triangulation constraint to generate more outstanding matches;Finally,to recall the matching pairs,dynamic guided matching is used and then submit the inliers after the PyRANSAC process.Multiple evaluation metrics are used and reported in the 1st place in the Track1 of CVPR Image-Matching Challenge Workshop.The results show that the proposed method has advanced performance in large-scale and challenging Phototourism benchmark.
文摘For the virtual environment (VE) to control remote robots through Internet, this paper proposes an operational idea based on virtual guides (VGs). The VGs consist of three types, line VG, plane VG, and body VG, which can greatly enhance the safety and flexibility of the man-machine system. Through the analysis of several common cases, the idea of the VGs are first introduced and described. Second, detailed descriptions of the three VGs are given, and then a uniform representation of all VGs is given. Finally, a typical experiment is designed and implemented according to the modes of video feedback, video&VE feedback, and video&VE&VG feedback. Experimental results show that the operation based on VEs and VGs have significant advantages over that based on video feedback, and VGs can greatly improve the ability of the VE to control remote robots, thus obtaining high and efficient man-machine cooperation.
文摘The paper is a part of wider investigation related to the application of basic sciences to the sustainable development of society.It deals with the presentation of knowledge to the real estate(fast growing business)about the local natural and man-made hazards in the near vicinity of any structure(inhabitant,recreation area,land,etc.)and their influence to the social safety and human comfort of life.The structure,necessary information and knowledge base for visible or hidden hazards about a guide for the real estate business is included.An example of application the knowledge about seismic hazard and related phenomena simplified to be more available to the non-specialists(such as real estate agents and companies)targeted to Sofia(the largest urban center and capital of Bulgaria)can attract and improve the learning abilities of the real estate for the society’s sake.
